Agent Skills › penpot/penpot › testing

testing

GitHub

强制实施 TDD 工作流和 Penpot 测试最佳实践，适用于功能实现、Bug 修复及行为修改。遵循红绿重构流程，要求为所有行为变更编写测试，确保代码质量与规范。

.agents/skills/testing/SKILL.md penpot/penpot

Trigger Scenarios

实现新功能或逻辑修复 Bug 修改现有功能添加边界情况处理

Install

npx skills add penpot/penpot --skill testing -g -y

More Options

Non-standard path

npx skills add https://github.com/penpot/penpot/tree/develop/.agents/skills/testing -g -y

Use without installing

npx skills use penpot/penpot@testing

指定 Agent (Claude Code)

npx skills add penpot/penpot --skill testing -a claude-code -g -y

安装 repo 全部 skill

npx skills add penpot/penpot --all -g -y

预览 repo 内 skill

npx skills add penpot/penpot --list

SKILL.md

Frontmatter

{
    "name": "testing",
    "description": "Enforce TDD workflow and testing best practices for Penpot. Use when implementing features, fixing bugs, or modifying behavior. Reads testing memory for full guidance."
}

Testing Skill

Enforces test-driven development and Penpot testing conventions.

When to Use

Implementing new logic or behavior
Fixing any bug (reproduction test required)
Modifying existing functionality
Adding edge case handling

Skip: Pure configuration changes, documentation updates, or static content with no behavioral impact.

Workflow

Follow TDD (Red → Green → Refactor) whenever practical:

RED — Write a failing test first
GREEN — Write minimal code to pass
REFACTOR — Clean up while tests stay green

For bug fixes, use the Prove-It Pattern: write a test that reproduces the bug, confirm it fails, implement the fix, confirm it passes.

Required Reading

Before writing any test, read:

.serena/memories/testing.md — cross-cutting testing principles, TDD workflow, anti-patterns, execution discipline
Module-specific testing memory for the affected module:
- mem:common/testing — CLJC unit tests
- mem:frontend/testing — CLJS unit tests, Playwright E2E
- mem:backend/testing — JVM clojure.test conventions
- mem:exporter/testing — exporter unit tests

Key Rules

Every behavior change needs a test
Test state, not interactions
DAMP over DRY — tests are specifications; duplication is OK if each test is self-contained and readable
Prefer Real > Fake > Stub > Mock
Arrange-Act-Assert structure
One assertion per concept
Never pipe test output to filters — redirect to file first
Register new test files in the module's runner/entrypoint